Intelligent doorbell connection method and related devices

Abstract

The present application provides a method for connecting an intelligent doorbell and related devices. The method includes: after receiving a doorbell event triggered by a guest, sending a device information query request to each terminal; receiving the device information returned by each terminal; determining a target terminal according to the device information returned by each terminal; and establishing a connection with the target terminal. The present application can determine the target terminal according to the device information of each terminal, and realize effective interaction between the intelligent doorbell and the terminal.

Description

Technical Field

[0001] This application relates to the technical field of smart home, and particularly to a method for connecting an intelligent doorbell and related devices. Background Art

[0002] With the popularization of the concept of smart home and the development of technology, intelligent doorbells are used more and more frequently. An intelligent doorbell includes hardware devices such as a camera, a speaker, and a microphone, and has functions of video monitoring and doorbell. When a guest visits, the intelligent doorbell collects information of the visiting guest through the camera and the microphone, and sends the collected information to the user's terminal (such as a mobile phone, a tablet, a large screen, etc.). Currently, the intelligent doorbell is generally bound to a terminal. For example, the intelligent doorbell is bound to a large screen, and the intelligent doorbell fixedly notifies the bound terminal of the information of the guest's visit. The method of making a visit notification according to the bound terminal has certain defects. For example, when the bound terminal is not in a working state (such as shutdown), the intelligent doorbell cannot effectively notify the user of the information of the guest's visit. Another example is that in some scenarios, the user is using the bound terminal (such as using a tablet to have a meeting) and does not want to be disturbed by the information of the guest's visit. Summary of the Invention

[0003] Embodiments of this application provide a method for connecting an intelligent doorbell and related devices, which can determine a target terminal according to device information and realize effective interaction between the intelligent doorbell and the terminal.

[0004] A first aspect of this application discloses a method for connecting an intelligent doorbell. The method includes:

[0005] After receiving a doorbell event triggered by a guest, sending a device information query request to each terminal;

[0006] Receiving the device information returned by each terminal;

[0007] Determining a target terminal according to the device information returned by each terminal;

[0008] Establishing a connection with the target terminal.

[0009] According to the method for connecting an intelligent doorbell provided by the embodiments of this application, when a guest visits, the intelligent doorbell obtains the device information of each terminal, determines a target terminal according to the device information of each terminal, and establishes a connection with the target terminal. The method for connecting an intelligent doorbell provided by the embodiments of this application selects a suitable terminal for connection, realizes effective interaction between the intelligent doorbell 10 and the terminal, and improves the user experience.

[0010] In some optional embodiments, after establishing the connection with the target terminal, the method further includes:

[0011] Send the collected voice of the guest to the target terminal.

[0012] In some alternative embodiments, after establishing the connection with the target terminal, the method further includes:

[0013] Send the collected image of the guest to the target terminal.

[0014] In some alternative embodiments, before sending the collected image of the guest to the target terminal, the method further includes:

[0015] Determine whether the target terminal includes a screen;

[0016] If the target terminal includes a screen, execute sending the collected image of the guest to the target terminal.

[0017] In some alternative embodiments, after establishing the connection with the target terminal, the method further includes:

[0018] Receive the user voice sent by the target terminal.

[0019] In some alternative embodiments, the sending the device information query request to each terminal includes:

[0020] Send the device information query request to each terminal by broadcasting.

[0021] In some alternative embodiments, the sending the device information query request to each terminal by broadcasting includes:

[0022] Send the device information query request to each terminal by local area network broadcast or Bluetooth broadcast.

[0023] In some alternative embodiments, the device information includes device type, usage scenario, screen status, speaker status, microphone status, connection information.

[0024] In some alternative embodiments, the determining the target terminal according to the device information returned by each terminal includes:

[0025] Make a decision on the device information returned by each terminal through a decision tree to obtain a terminal suitable for connection;

[0026] Determine the target terminal according to the terminal suitable for connection.

[0027] In some alternative embodiments, if there are multiple terminals suitable for connection, the determining the target terminal according to the terminals suitable for connection includes:

[0028] Select one terminal from the suitable terminals to be connected as the target terminal according to the preset device priority.

[0029] In some alternative embodiments, before making a decision on the device information returned by each terminal through the decision tree, the method further includes:

[0030] Obtain sample data, where the sample data includes samples of multiple known device information and classification results, and the device information of each sample includes multiple feature attributes;

[0031] Establish the decision tree according to the sample data.

[0032] In some alternative embodiments, establishing the decision tree according to the sample data includes:

[0033] Calculate the information entropy of the root node of the decision tree and each feature attribute;

[0034] Calculate the information gain of each feature attribute according to the information entropy of each feature attribute;

[0035] Use the feature attribute with the largest information gain as the classification node of the decision tree.

[0036] A second aspect of the present application discloses a computer-readable storage medium, including computer instructions, which when running on the smart doorbell, cause the smart doorbell to execute the smart doorbell connection method as described in the first aspect.

[0037] A third aspect of the present application discloses a smart doorbell, which includes a processor and a memory. The memory is used to store instructions, and the processor is used to call the instructions in the memory, so that the smart doorbell executes the smart doorbell connection method as described in the first aspect.

[0038] A fourth aspect of the present application discloses a chip system, which is applied to a smart doorbell; the chip system includes an interface circuit and a processor; the interface circuit and the processor are interconnected by a line; the interface circuit is used to receive signals from the memory of the smart doorbell and send signals to the processor, and the signals include computer instructions stored in the memory; when the processor executes the computer instructions, the chip system executes the smart doorbell connection method as described in the first aspect.

[0039] A fifth aspect of the present application discloses a computer program product, which when running on a computer, causes the computer to execute the smart doorbell connection method as described in the first aspect.

[0040] The sixth aspect of the present application discloses a device, which has the function of implementing the intelligent doorbell behavior in the method provided in the above first aspect. The function can be implemented by hardware or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above functions.

[0041] It should be understood that the computer-readable storage medium described in the second aspect provided above, the intelligent doorbell described in the third aspect, the chip system described in the fourth aspect, the computer program product described in the fifth aspect, and the device described in the sixth aspect all correspond to the method in the first aspect above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method provided above, and will not be elaborated here. Description of the Drawings

[0042] Figure 1 It is a schematic diagram of the application scenario of the intelligent doorbell connection method provided by the embodiment of the present application.

[0043] Figure 2 It is a functional architecture diagram of the intelligent doorbell provided by the embodiment of the present application.

[0044] Figure 3 It is a flowchart of the intelligent doorbell connection method provided by the embodiment of the present application.

[0045] Figure 4 It is a schematic diagram of the intelligent doorbell sending a device information query request to each terminal and each terminal returning device information to the intelligent doorbell.

[0046] Figure 5 It is a schematic diagram of the device priority set by the embodiment of the present application.

[0047] Figure 6 It is a flowchart of determining the target terminal through a decision tree provided by the embodiment of the present application.

[0048] Figure 7 It is a schematic diagram of the sample data for establishing a decision tree provided by the embodiment of the present application.

[0049] Figure 8 It is a schematic diagram of splitting according to the usage scenario priority.

[0050] Figure 9 It is a schematic diagram of the structure of the intelligent doorbell provided by the embodiment of the present application. Detailed Embodiments

[0051] For ease of understanding, some descriptions of concepts related to the embodiments of the present application are exemplarily given for reference.

[0052] It should be noted that in this application, "at least one" means one or more, and "a plurality" means two or more than two. "And / or" describes the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone, where A and B can be singular or plural. The terms "first", "second", "third", "fourth", etc. (if any) in the specification, claims and drawings of this application are used to distinguish similar objects, rather than to describe a specific order or sequence.

[0053] To better understand the intelligent doorbell connection method and related devices provided in the embodiments of this application, the application scenarios of the intelligent doorbell connection method of this application will be described first below.

[0054] Figure 1 It is a schematic diagram of the application scenario of the intelligent doorbell connection method provided in the embodiments of this application.

[0055] As Figure 1 shown, the intelligent doorbell 10 is installed on the door. There are multiple terminals indoors, such as the mobile phone carried by the user, wearable devices (such as watches), personal computers (Personal Computer, PC), tablets in the study and bedroom, large screens and speakers in the living room, etc.

[0056] The intelligent doorbell 10 includes a camera 101, a microphone 102, and a speaker 103. The camera 101 is used to collect images of guests. The microphone 102 is used to collect the voices of guests. The speaker 103 is used to play the voices of users (such as mobile phone users).

[0057] According to the intelligent doorbell connection method provided in the embodiments of this application, when a guest visits, the intelligent doorbell 10 obtains device information such as the device type, usage scenario, and screen status of each terminal, determines the target terminal according to the device information of each terminal, establishes a connection with the target terminal, and sends the images of the guests collected by the camera 101 of the intelligent doorbell 10 and the voices of the guests collected by the microphone 102 to the target terminal. The intelligent doorbell connection method provided in the embodiments of this application selects a suitable terminal for connection, realizes effective interaction between the intelligent doorbell 10 and the terminal, and improves the user experience.

[0058] Figure 2 It is a functional architecture diagram of the intelligent doorbell applying the embodiments of this application.

[0059] As Figure 2 described, in an embodiment of this application, the intelligent doorbell 20 includes an event notification module 201, an information collection module 202, a connection decision module 203, and a connection establishment module 204.

[0060] The event notification module 201 is used to receive doorbell events triggered by guests and send device information query requests to surrounding terminals. The event notification module 201 can send device information query requests through methods such as local area network broadcasting and Bluetooth broadcasting. Local area network broadcasting can be used to send device information query requests to local area network devices, and Bluetooth broadcasting can be used to send device information query requests to Bluetooth devices. The event notification module 201 supports communication protocol extension to adapt to sending device information queries to other devices.

[0061] The information collection module 202 is used to collect device information of each terminal. In an embodiment of the present application, the device information of the terminal may include device type, usage scenario, screen status, speaker status, microphone status, connection information, etc.

[0062] The device type may include large screens, speakers, mobile phones, wearable devices, PCs, and tablets.

[0063] The usage scenario may include leisure and entertainment, office and study, social, and stopped working.

[0064] The screen status may include screen on and screen off.

[0065] The speaker status may include playing sound and muted.

[0066] The microphone status may include on and off.

[0067] The connection information may include supported communication protocols, Internet Protocol (IP) addresses, port numbers, etc.

[0068] In other embodiments of the present application, the device information of the terminal may further include other information. For example, the device information of the terminal may include the location information of the terminal. According to the location information of the terminal, it can be determined that the terminal is located in the living room, bedroom, kitchen, etc. (it is more suitable to establish a connection when the terminal is located in the living room than in other locations). Another example is that the device information of the terminal may include the user perception information of the terminal. The user perception information of the terminal may include perceiving that there is someone around and perceiving that there is no one around, and may also include perceiving the user status, such as perceiving whether the user is focused on the terminal (it is more suitable to establish a connection when the user is focused on the terminal than when the user is not focused on the terminal). It can be detected whether the user is facing the terminal. If the user is facing the terminal, it is confirmed that the user is focused on the terminal. Otherwise, if the user is not facing the terminal, it is confirmed that the user is not focused on the terminal.

[0069] The connection decision module 203 is used to determine the target terminal according to the device information of each terminal. The connection decision module 203 can determine the target terminal according to the device type, usage scenario, screen status, speaker status, microphone status, etc. In an embodiment of the present application, the connection decision module 203 can determine the target terminal through a decision tree. The connection decision module 203 can make a decision on the device information of the terminal through a decision tree, obtain the terminal suitable for connection, and determine the target terminal according to the terminal suitable for connection. If multiple terminals suitable for connection are obtained through the decision tree, one terminal can be selected from the multiple terminals suitable for connection as the target terminal according to the device priority. If one terminal suitable for connection is obtained through the decision tree, the terminal suitable for connection is used as the target terminal.

[0070] In an embodiment of the present application, the usage scenario, screen status, speaker status, and microphone status of the terminal can be used as the characteristic attributes (i.e., the input of the decision tree) of the decision tree for decision-making to obtain the terminal suitable for connection. In other embodiments of the present application, other device information can be used as the characteristic attributes of the decision tree. For example, the device type, usage scenario, screen status, speaker status, and microphone status of the terminal can be used as the characteristic attributes of the decision tree. Another example is that the location information, user perception information, usage scenario, screen status, speaker status, and microphone status of the terminal can be used as the characteristic attributes of the decision tree.

[0071] In Figure 2 the illustrated embodiment, the connection decision module 203 is deployed in the smart doorbell. In other embodiments of the present application, the connection decision module 203 can be deployed in the terminal, for example, deployed in the Figure 1 illustrated PC. The connection decision module 203 can also be deployed in the cloud. The information collection module 202 can send the device information of each terminal to the terminal or the cloud where the connection decision module 203 is deployed for decision-making by the terminal or the cloud where the connection decision module 203 is deployed.

[0072] The connection establishment module 204 is used to establish a connection with the target terminal. In an embodiment of the present application, the connection establishment module 204 can establish a connection with the target terminal according to the connection information of the target terminal. For example, if the target device is a local area network device (i.e., supports the local area network communication protocol), the connection establishment module 204 establishes a connection with the target terminal through the local area network. If the target terminal is not a local area network device, the connection establishment module 204 establishes a connection with the target terminal through Peer-to-Peer (P2P). For example, if the target device is not a local area network device and supports the Bluetooth communication protocol, the connection establishment module 204 establishes a connection with the target terminal through Bluetooth.

[0073] The connection establishment module 204 can also be used to send the image of the guest collected by the camera 101 and the voice of the guest collected by the microphone 102 of the smart doorbell 10 to the target terminal based on the establishment of a connection with the target terminal.

[0074] Figure 3 is a flowchart of the smart doorbell connection method provided by the embodiments of the present application.

[0075] 301. The guest triggers the doorbell event.

[0076] When a guest visits, the guest can press the ringing button of the smart doorbell, thereby triggering the doorbell event.

[0077] 302. The smart doorbell sends a device information query request to each terminal.

[0078] The smart doorbell sends a device information query request to each terminal in a broadcast manner. The smart doorbell can send a device information query request through methods such as local area network broadcast and Bluetooth broadcast. Local area network broadcast can be used to send a device information query request to local area network devices, and Bluetooth broadcast can be used to send a device information query request to Bluetooth devices.

[0079] 303. Each terminal returns device information to the smart doorbell.

[0080] In the embodiments of the present application, the device information of the terminal may include device type, usage scenario, screen status, speaker status, microphone status, connection information, etc.

[0081] The device type may include large screen, speaker, mobile phone, wearable device, PC, tablet.

[0082] The usage scenario may include entertainment, office study, social, stop working.

[0083] The screen status may include screen on and screen off. If the terminal does not include a screen, the returned screen status may be empty.

[0084] The speaker status may include playing sound and mute.

[0085] The microphone status may include on and off.

[0086] The connection information may include supported communication protocols, IP addresses, port numbers, etc.

[0087] Figure 4 is a schematic diagram of the smart doorbell sending a device information query request to each terminal and each terminal returning device information to the smart doorbell.

[0088] Such as Figure 4As shown, the smart doorbell sends a device information query request to a large screen, a speaker, a PC, a tablet, a mobile phone, and a wearable device, and the large screen, the speaker, the PC, the tablet, the mobile phone, and the wearable device return their respective device information to the smart doorbell.

[0089] 304. The smart doorbell determines a target terminal based on the device information of each terminal.

[0090] In an embodiment of the present application, the number of target terminals can be one. The smart doorbell can determine a suitable terminal to connect based on the device information of each terminal. If the smart doorbell determines that the suitable terminal to connect is one, the suitable terminal to connect is used as the target terminal. If the smart doorbell determines that there are multiple suitable terminals to connect, one terminal is selected as the target terminal from the multiple suitable terminals according to the preset device priority.

[0091] Figure 5 It is a schematic diagram of the device priority set in the embodiment of the present application. As Figure 5 shown, the priority from high to low is: large screen, mobile phone / wearable device, speaker, PC / tablet. Among them, the large screen has the highest priority, and the PC and the tablet have the lowest priority. The mobile phone and the wearable device have the same priority, and the PC and the tablet have the same priority. For example, if the smart doorbell determines that the suitable terminals to connect include a tablet and a mobile phone, according to Figure 5 the device priority shown, the smart doorbell selects the mobile phone as the target terminal.

[0092] The user can customize the device priority. When a new terminal (not in the priority) is added, the user can add the new terminal to the existing priority. For example, currently there are four priorities: large screen, mobile phone / wearable device, speaker, PC / tablet, and the new added device can be added to one of them. Or, the user can add a new priority. For example, a new priority is added between the mobile phone / wearable device and the speaker, and the new added terminal is added to the newly added priority.

[0093] The device priority can be set according to various factors. For example, it can be set according to whether the terminal has a screen, the location of the terminal, etc. For example, it can be set that the device priority of a terminal with a screen is higher than that of a terminal without a screen, and the device priority of a terminal located in the living room is higher than that of terminals in other locations.

[0094] In one embodiment of the present application, a priority policy can be set, and the smart doorbell can generate the device priority of the terminal according to the priority policy. For example, a first condition can be set to define that the terminal satisfying the first condition has a first device priority, a second condition can be set to define that the terminal satisfying the second condition has a second device priority, and a third condition can be set to define that the terminal satisfying the third condition has a third device priority. The smart doorbell determines the conditions satisfied by the terminal, thereby determining the device priority of the terminal.

[0095] In one embodiment of the present application, the smart doorbell can make decisions on the device information of each terminal through a decision tree to determine the target terminal. The specific content of determining the target terminal through the decision tree will be described in Figure 6 it.

[0096] In other embodiments of the present application, the smart doorbell can determine the target terminal through other means. For example, the target terminal can be determined through a convolutional neural network.

[0097] 305, the smart doorbell establishes a connection with the target terminal.

[0098] In an embodiment of the present application, the smart doorbell can establish a connection with the target terminal according to the connection information of the target terminal. For example, if the target device is a local area network device (i.e., a device that can communicate effectively through the local area network), the smart doorbell establishes a connection with the target terminal through the local area network. If the target terminal is not a local area network device, the smart doorbell establishes a connection with the target terminal through P2P. For example, if the target device is not a local area network device and supports the Bluetooth communication protocol, the smart doorbell establishes a connection with the target terminal through Bluetooth.

[0099] 306, if the target terminal has a screen, the smart doorbell sends the image of the guest collected by the camera to the target terminal.

[0100] For example, if the target terminal is a large screen, the smart doorbell sends the collected image of the guest to the large screen.

[0101] The smart doorbell can collect the image of the guest after the guest triggers the doorbell event. Or, the smart doorbell can collect the image of the guest when it detects that there is a guest outside the door. The smart doorbell can include a distance sensor or a proximity light sensor for detecting whether there is a guest outside the door.

[0102] The device information returned by the terminal may include the screen status. If the terminal does not include a screen, the returned screen status may be empty. The smart doorbell can determine whether the destination terminal has a screen based on the screen status returned by the target terminal. If the screen status returned by the target terminal is empty, it is determined that the target terminal has no screen. Otherwise, if the screen status returned by the target terminal is on or off, it is determined that the target terminal has a screen. Alternatively, the smart doorbell can determine whether the target terminal has a screen based on the device type returned by the target terminal. If the device type returned by the target terminal is a preset type (such as a speaker), it is determined that the target terminal has no screen.

[0103] 307, The smart doorbell receives the user voice sent by the target terminal and sends the voice of the guest collected by the microphone to the target terminal for doorbell intercom.

[0104] For example, if the target terminal is a large screen, the smart doorbell receives the user voice sent by the large screen and sends the collected voice of the guest to the large screen.

[0105] The smart doorbell can collect the voice of the guest after receiving the user voice sent by the target terminal. Alternatively, the smart doorbell can collect the voice of the guest after the guest triggers the doorbell event.

[0106] According to Figure 3 The smart doorbell connection method shown, the smart doorbell determines the target terminal according to the device information of each terminal, avoiding the ineffective interaction between the smart doorbell and the terminal and improving the user experience.

[0107] Figure 6 It is a flowchart for determining the target terminal by the decision tree provided by the embodiment of the present application.

[0108] 601, Obtain sample data.

[0109] The sample data includes multiple samples of known device information and classification results. In an embodiment of the present application, each sample includes five device information, namely device type, usage scenario, screen status, speaker status, and microphone status, and a classification result. In an embodiment of the present application, the device type, usage scenario, screen status, speaker status, and microphone status can be used as the feature attributes of the decision tree. In another embodiment of the present application, the usage scenario, screen status, speaker status, and microphone status can be used as the feature attributes of the decision tree. In other embodiments of the present application, other device information of the terminal can also be used as the feature attributes of the decision tree. For example, the location information, user perception information, usage scenario, screen status, speaker status, and microphone status of the terminal can be used as the feature attributes of the decision tree.

[0110] The feature attributes are used to determine the branching conditions of the decision tree.

[0111] The device types may include large screens, speakers, mobile phones, wearable devices, PCs, and tablets.

[0112] The usage scenarios may include entertainment, office work and study, social interaction, and work suspension.

[0113] The screen states may include the screen being on and the screen being off.

[0114] The speaker states may include playing sound and being muted.

[0115] The microphone states may include being on and being off.

[0116] The classification results of the samples include response and non - response. Samples with a classification result of response are positive samples, indicating that the terminal can respond to the connection (i.e., is suitable for connection), and samples with a classification result of non - response are negative samples, indicating that the terminal cannot respond to the connection (i.e., is not suitable for connection).

[0117] Figure 7 It is a schematic diagram of the sample data used in the embodiments of this application to establish a decision tree. As Figure 7 shown, the sample data contains 26 samples. Classified by device type, there are 5 large screens, 5 PCs, 3 wearable devices, 5 tablets, 5 mobile phones, and 3 speakers; classified by usage scenario, there are 8 for office work and study, 4 for social interaction, 6 for work suspension, and 8 for entertainment; classified by screen state, there are 18 with the screen on and 8 with the screen off; classified by speaker state, there are 18 playing sound and 8 being muted; classified by microphone state, there are 11 being on and 15 being off; classified by classification result, there are 11 responses and 15 non - responses.

[0118] 602. Establish a decision tree according to the sample data.

[0119] In an embodiment of this application, the Iterative Dichotomiser 3 (ID3) algorithm may be used to establish a decision tree. The ID3 algorithm is based on information theory and uses information entropy and information gain as the measurement criteria to achieve the inductive classification of data.

[0120] In an embodiment of this application, establishing a decision tree according to the sample data may include:

[0121] (1) Calculate the information entropy of the root node of the decision tree and each feature attribute.

[0122] A decision tree includes a root node, internal nodes, and leaf nodes. The root node contains the entire set of samples. Each internal node corresponds to a feature attribute, indicating a decision - making judgment based on that feature attribute. Each leaf node represents a classification result.

[0123] Information entropy is used to measure the degree of uncertainty of a random variable and can be used to solve the problem of measuring the amount of information. The larger the information entropy, the greater the uncertainty of the information and the greater the amount of information. Conversely, the smaller the information entropy, the smaller the uncertainty of the information and the smaller the amount of information.

[0124] In an embodiment of the present application, the information entropy of the root node of the decision tree and each feature attribute is calculated as follows:

[0125]

[0126] where |y| represents the number of categories of the classification result, D represents the sample set, and p k represents the proportion of the k-th type of samples in the sample set D.

[0127] Continuing with the Figure 7 sample set shown as an example, for the root node, the corresponding sample set includes 26 samples, the classification result includes 2 categories, so |y| = 2. Among them, there are 11 positive samples, and the proportion of positive samples is 11 / 26, and 15 negative samples, and the proportion of negative samples is 15 / 26. The information entropy of the root node is:

[0128]

[0129] where Dr represents the sample set corresponding to the root node, that is, 26 samples.

[0130] The information entropy corresponding to each value of the feature attribute can be calculated, and the information entropy of the feature attribute can be calculated according to the information entropy corresponding to each value of the feature attribute.

[0131] In an embodiment of the present application, the information entropy of the feature attribute can be equal to the weighted sum of the information entropies corresponding to all values of the feature attribute, and the information entropy of the feature attribute can be expressed as:

[0132]

[0133] where, Da represents the sample set corresponding to the feature attribute a, D v represents the sample set corresponding to a value of the feature attribute, |Dr| represents the number of samples in the sample set corresponding to the root node, and |D v | represents the number of samples in the sample set corresponding to a value of the feature attribute, and Ent(D v ) represents the information entropy corresponding to a value of the feature attribute.

[0134] Taking the usage scenario as an example, the usage scenario includes four values: leisure and entertainment, office and study, social, and stop working, and the corresponding sample subsets are:

[0135] D11: Leisure and entertainment, with a total of 8 samples, including 7 positive samples and 1 negative sample;

[0136] D12: Office work and study, with a total of 8 samples, including 4 positive samples and 4 negative samples;

[0137] D13: Social, with a total of 4 samples, including 0 positive samples and 4 negative samples;

[0138] D14: Stop working, with a total of 6 samples, including 0 positive samples and 6 negative samples.

[0139] Then the information entropy corresponding to leisure and entertainment, Ent(D11), is:

[0140]

[0141] Similarly, the information entropy Ent(D12) corresponding to office work and study, the information entropy Ent(D13) corresponding to social, and the information entropy Ent(D14) corresponding to stop working can be calculated.

[0142] The information entropy of the usage scenario can be:

[0143]

[0144] Similarly, the information entropy of the device type (which can be expressed as Ent(D2)), the information entropy of the screen state (which can be expressed as Ent(D3)), the information entropy of the speaker state (which can be expressed as Ent(D4)), and the information entropy of the microphone state (which can be expressed as Ent(D5)) can be calculated.

[0145] (2) Calculate the information gain of each feature attribute.

[0146] Subtract the information entropy of the feature attribute from the information entropy of the root node to obtain the information gain of the feature attribute. The information gain calculation is as follows:

[0147]

[0148] Among them, a represents the feature attribute.

[0149] The information gain indicates how much information a feature can bring to the classification system. The more information it brings, the more important the feature is, and the greater the corresponding information gain.

[0150] Continuing with the Figure 7 sample data shown as an example, the information gain of the usage scenario can be calculated:

[0151]

[0152] Similarly, the information gain Gain(Dr, device type), the information gain Gain(Dr, screen status), the information gain Gain(Dr, speaker status), and the information gain Gain(Dr, microphone status) of the device type can be calculated.

[0153] (3) Arrange each characteristic attribute in descending order of information gain, and use the characteristic attribute with the largest information gain as the classification node of the decision tree.

[0154] According to the descending order of information gain, the characteristic attribute with a larger information gain is preferentially selected as the characteristic attribute for division. Each branch node is further divided, and finally a decision tree is obtained.

[0155] Figure 8 It is a schematic diagram of splitting by usage scenario first.

[0156] As Figure 8 shown, the information gain of the usage scenario is the largest. The usage scenario is preferentially selected to divide the sample set, and the usage scenario is split into four branches according to leisure and entertainment, office and study, social, and stop working. The sub-node corresponding to stop working is a leaf node, and the classification result is non-response. The sub-nodes corresponding to leisure and entertainment, office and study, and social need to be determined by the same method.

[0157] 603. Make decisions on the device information returned by each terminal through the decision tree to obtain the decision results of each terminal.

[0158] Use the device information returned by each terminal to obtain the result of whether the device responds according to the decision tree. If there are multiple devices, filter according to the device priority and connect the obtained results.

[0159] 604. Determine the target terminal according to the decision results of each terminal.

[0160] In an embodiment of the present application, if the terminal suitable for connection determined by the decision tree is one, use this suitable terminal as the target terminal. If the terminals suitable for connection determined by the decision tree are multiple, select one terminal from the multiple suitable terminals as the target terminal according to the preset device priority.

[0161] The smart doorbell can send the image of the guest collected by the camera to the target terminal, and can also send the voice of the guest collected by the microphone to the target terminal.

[0162] The smart doorbell can determine whether the target terminal has a screen. If the target terminal has a screen, send the image of the guest collected by the camera to the target terminal. Otherwise, if the target terminal does not have a screen, do not send the image of the guest to the target terminal.

[0163] Figure 9 is a schematic structural diagram of the smart doorbell provided by an embodiment of the present application. As Figure 9 shown, the smart doorbell 90 may include: a processor 901, a memory 902, a wireless communication module 903, a ringing button 904, a speaker 905, a microphone 906, a human body sensing sensor 907, a camera 908, a power supply device 909, etc. It can be understood that the structure illustrated in this embodiment does not constitute a specific limitation on the smart doorbell 90. In other embodiments of the present application, the smart doorbell 90 may include more or fewer components than those shown in the figure, or combine certain components, or split certain components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0164] The processor 901 may include one or more processing units. For example, the processor 901 may include an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, a video codec, a digital signal processor (DSP), a baseband processor, a display processing unit (DPU), and / or a neural-network processing unit (NPU), etc. Among them, different processing units may be independent devices or integrated in one or more processors.

[0165] A memory may be provided in the processor 901 for storing instructions and data. In some embodiments, the memory in the processor 901 is a cache memory. This memory may save the instructions or data that the processor 901 has just used or recycled. If the processor 901 needs to use the instruction or data again, it can directly call it from this memory, avoiding repeated access, reducing the waiting time of the processor 901, and improving the efficiency of the smart doorbell 90.

[0166] In some embodiments, the processor 901 may include one or more interfaces. The interfaces may include an inter-integrated circuit (I2C) interface, an inter-integrated circuit sound (I2S) interface, a pulse code modulation (PCM) interface, a universal asynchronous receiver / transmitter (UART) interface, a mobile industry processor interface (MIPI), a general-purpose input / output (GPIO) interface, a subscriber identity module (SIM) interface, and / or a universal serial bus (USB) interface, etc. It can be understood that the interface connection relationship between the modules illustrated in the embodiments of the present invention is only for illustrative purposes and does not constitute a structural limitation on the smart doorbell 90. In other embodiments of the present application, the smart doorbell 90 may also adopt different interface connection methods in the above embodiments, or a combination of multiple interface connection methods.

[0167] The memory 902 may be used to store one or more computer programs, and the one or more computer programs include instructions. The processor 901 may execute relevant actions in the embodiments of the present application by running the instructions stored in the memory 902. The memory 902 may include a program storage area and a data storage area. Among them, the program storage area may store an operating system; the program storage area may also store one or more application programs. The data storage area may store data created during the use of the smart doorbell 90. In addition, the memory 902 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, a universal flash storage (UFS), etc. In some embodiments, the processor 901 may execute various functional applications and data processing by running the instructions stored in the memory 902, and / or the instructions stored in the memory provided in the processor 901.

[0168] The wireless communication function of the smart doorbell 90 can be realized by the wireless communication module 903. The wireless communication module 903 can provide wireless communication solutions including wireless local area networks (WLAN), Bluetooth, global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), infrared technology (IR), etc. applied to the smart doorbell 90. The wireless communication module 903 can be one or more devices integrating at least one communication processing module. The wireless communication module 903 in the embodiment of the present application is used to realize the sending and receiving functions of the smart doorbell.

[0169] The bell button 904 is used to sound a bell when the guest presses the button to remind the user that the guest is visiting.

[0170] The smart doorbell 90 can realize the intercom function between the user and the guest through the speaker 905 and the microphone 906. Among them, the speaker 905 is used to convert the user's digital audio information into an analog audio signal, that is, to play the user's voice. The microphone 906 is used to convert the guest's analog audio signal into digital audio information, that is, to collect the guest's voice. The smart doorbell 90 can be provided with at least one microphone 906. In other embodiments, the smart doorbell 90 can be provided with two microphones 906, in addition to collecting sound signals, it can also realize the noise reduction function. In other embodiments, the smart doorbell 90 can also be provided with three, four or more microphones 906 to realize the collection of sound signals, noise reduction, and can also identify the sound source to realize directional recording functions, etc.

[0171] The human body sensing sensor 907 is used to sense whether there is a guest outside the door. The human body sensing sensor 907 may include a distance sensor, a proximity light sensor, etc. The distance sensor is used to measure the distance. The smart doorbell 90 can measure the distance by infrared or laser. The proximity light sensor may include a light emitting diode (LED) and a light detector. The light emitting diode may be an infrared light emitting diode. The light detector may be a photodiode. The smart doorbell 90 emits infrared light outward through the light emitting diode. The smart doorbell 90 uses the light detector to detect infrared reflected light from nearby objects. When sufficient reflected light is detected, it can be determined that there is a guest outside the door. When insufficient reflected light is detected, the smart doorbell 90 can determine that there is no guest outside the door.

[0172] The intelligent doorbell 90 can implement a shooting function through one or more cameras 908, such as shooting guests. In some embodiments, the camera 908 can be an infrared night vision camera, and the infrared night vision camera has infrared night vision capabilities.

[0173] The intelligent doorbell 90 further includes a power supply device 909 (such as a battery) for powering each component.

[0174] Figure 9 The intelligent doorbell 90 described in [reference] can be used to implement part or all of the processes in the embodiments of the present application. For relevant explanations, refer to the foregoing embodiments and will not be elaborated here.

[0175] This embodiment also provides a computer storage medium. Computer instructions are stored in the computer storage medium. When the computer instructions run on the intelligent doorbell, the intelligent doorbell executes the above - related method steps to implement the intelligent doorbell connection method in the above - mentioned embodiment.

[0176] This embodiment also provides a computer program product. When the computer program product runs on the intelligent doorbell, the intelligent doorbell executes the above - related steps to implement the intelligent doorbell connection method in the above - mentioned embodiment.

[0177] In addition, an embodiment of the present application also provides a device, which can specifically be a chip, a component or a module. The device may include a processor and a memory connected to each other. Among them, the memory is used to store computer - executable instructions. When the device runs, the processor can execute the computer - executable instructions stored in the memory so that the chip executes the intelligent doorbell connection method in each of the above - mentioned method embodiments.

[0178] Among them, the intelligent doorbell, the computer storage medium, the computer program product or the chip provided in this embodiment are all used to execute the corresponding methods provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding methods provided above and will not be elaborated here.

[0179] Through the description of the above - mentioned implementation manners, those skilled in the art can clearly understand that for the convenience and conciseness of description, only the above - mentioned division of each functional module is used as an example for illustration. In practical applications, the above - mentioned functions can be allocated to different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above.

[0180] In several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the module or unit is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces. The indirect coupling or communication connection of the device or unit can be in electrical, mechanical or other forms.

[0181] The unit described as a separate component may or may not be physically separated. The component displayed as a unit may be a physical unit or multiple physical units, that is, it may be located in one place, or it may be distributed to multiple different places. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0182] In addition, each functional unit in various embodiments of this application can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0183] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiments of this application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. The software product is stored in a storage medium and includes several instructions for causing a device (which can be a single-chip microcomputer, a chip, etc.) or a processor to execute all or part of the steps of the methods described in various embodiments of this application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks, or optical discs that can store program codes.

[0184] As described above, it is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any change or replacement within the technical scope disclosed in this application should be covered by the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claimed rights.

Claims

1. An intelligent doorbell connection method, characterized in that, the method includes: After receiving the doorbell event triggered by the guest, send a device information query request to each terminal; Receive the device information returned by each terminal, where the device information includes device type, usage scenario, screen status, speaker status, microphone status, connection information, and user perception information; Determine the target terminal according to the device type, the usage scenario, the screen status, the speaker status, the microphone status, the connection information, and the user perception information; Establish a connection with the target terminal.

2. The intelligent doorbell connection method according to claim 1, characterized in that, after establishing the connection with the target terminal, the method further includes: Send the collected voice of the guest to the target terminal.

3. The intelligent doorbell connection method according to claim 1 or 2, characterized in that, after establishing the connection with the target terminal, the method further includes: Send the collected image of the guest to the target terminal.

4. The intelligent doorbell connection method according to claim 3, characterized in that, before sending the collected image of the guest to the target terminal, the method further includes: Determine whether the target terminal includes a screen; If the target terminal includes a screen, execute sending the collected image of the guest to the target terminal.

5. The intelligent doorbell connection method according to any one of claims 1 to 4, characterized in that, after establishing the connection with the target terminal, the method further includes: Receive the user voice sent by the target terminal.

6. The intelligent doorbell connection method according to claim 1, characterized in that, the sending a device information query request to each terminal includes: Send a device information query request to each terminal by broadcasting.

7. The intelligent doorbell connection method according to claim 6, characterized in that, the sending a device information query request to each terminal by broadcasting includes: Send a device information query request to each terminal by local area network broadcast or Bluetooth broadcast.

8. The intelligent doorbell connection method according to claim 1, characterized in that, the determining the target terminal according to the device information returned by each terminal includes: Make a decision on the device information returned by each terminal through a decision tree to obtain a suitable terminal for connection; Determine the target terminal according to the suitable terminal for connection.

9. The intelligent doorbell connection method according to claim 8, characterized in that, if there are multiple suitable terminals for connection, the determining the target terminal according to the suitable terminals for connection includes: Select one terminal from the suitable terminals for connection as the target terminal according to the preset device priority.

10. The intelligent doorbell connection method according to claim 8, characterized in that, before making a decision on the device information returned by each terminal through a decision tree, the method further includes: Obtain sample data, where the sample data includes samples of multiple known device information and classification results, and the device information of each sample includes multiple feature attributes; Build the decision tree according to the sample data.

11. The intelligent doorbell connection method according to claim 10, wherein, the building of the decision tree according to the sample data includes: calculating the information entropy of the root node of the decision tree and each feature attribute; calculating the information gain of each feature attribute according to the information entropy of each feature attribute; taking the feature attribute with the largest information gain as the classification node of the decision tree.

12. A computer-readable storage medium, wherein, it includes computer instructions, and when the computer instructions run on the intelligent doorbell, the intelligent doorbell is enabled to execute the intelligent doorbell connection method according to any one of claims 1 to 11.

13. An intelligent doorbell, wherein, the intelligent doorbell includes a processor and a memory, the memory is used for storing instructions, and the processor is used for calling the instructions in the memory, so that the intelligent doorbell executes the intelligent doorbell connection method according to any one of claims 1 to 11.

14. A chip system, the chip system is applied to an intelligent doorbell; the chip system includes an interface circuit and a processor; the interface circuit and the processor are interconnected by a line; the interface circuit is used for receiving a signal from the memory of the intelligent doorbell and sending the signal to the processor, and the signal includes computer instructions stored in the memory; when the processor executes the computer instructions, the chip system executes the intelligent doorbell connection method according to any one of claims 1 to 11.

Images